6th International Workshop on

Interactive Adaptive Learning (IAL2022)

Co-Located With ECML PKDD 2022

23 September 2022 - Grenoble, France

View program and papers

Image © by Archangel12 (CC-BY-2.0)

Topic

Science, technology, and commerce increasingly recognise the importance of machine learning approaches for data-intensive, evidence-based decision making.

Science, technology, and commerce increasingly recognise the importance of machine learning approaches for data-intensive, evidence-based decision making. Moreover, the number of machine learning applications and the volumes of data increase permanently. Nevertheless, the capacities of processing systems, human supervisors, or domain experts remain limited in real-world applications. Furthermore, many applications require a fast reaction to new situations, which means that first predictive models need to be available even if little data is yet available. Therefore, approaches that optimise the whole learning process are needed, including the interaction with human supervisors, processing systems, and data of various kind and at different timings: techniques for estimating the impact of additional resources (e.g. data) on the learning progress; methods for active selection of the information processed or queried; techniques for reusing knowledge across time, domains, or tasks, by identifying similarities and adaptation to changes between them; methods for making use of different types of information, such as labelled or unlabelled data, constraints, or domain knowledge. Such techniques are studied, for example, in the fields of adaptive, active, semi-supervised, and transfer learning -- mostly in separate lines of research. Combinations that are capable of operating under various constraints, and thereby address the inherent real-world challenges of volume, velocity, and variability of data and data mining systems, are rarely reported. Therefore, this workshop aims to bring together researchers and practitioners from these different areas, and to stimulate research in interactive and adaptive machine learning systems as a whole. It continues a successful series of events at ECML PKDD 2017 in Skopje (Workshop and Tutorial), IJCNN 2018 in Rio (Tutorial), ECML PKDD 2018 in Dublin (Workshop), ECML PKDD 2019 in Würzburg (Workshop and Tutorial), and ECML PKDD 2020 (hosted in Ghent, online Workshop).

The workshop aims at discussing techniques and approaches for optimising the whole learning process, including the interaction with human supervisors, processing systems, and includes adaptive, active, semi-supervised, and transfer learning techniques, and combinations thereof in interactive and adaptive machine learning systems make the topic of this workshop. Our objective is to bridge the communities researching and developing these techniques and systems in machine learning and data mining. Therefore, we welcome contributions that present a new problem setting, propose a novel approach, or report experience with the practical deployment of such a system and raise unsolved questions to the research community.

In particular, we welcome contributions that address aspects including, but not limited to:

    Novel Techniques for Active, Semi-Supervised, Transfer, or Weakly Supervised Learning
  • methods for big, evolving, or streaming data,
  • methods for recent complex model structures such as deep learning neural networks or recurrent neural networks,
  • methods for interacting with imperfect or multiple oracles, e.g. learning from crowds,
  • methods for incorporating domain knowledge and constraints,
  • methods for timing the interaction and for combining different types of information,
  • online and ensemble methods for evolving models and systems, with specific switching and fusion techniques, and (inter-)active data integration techniques,
  • Innovative Use and Applications of Active, Semi-Supervised, Transfer, or Weakly Supervised Learning
  • for filtering, forgetting, resampling,
  • for active class or feature selection, e.g. from multi-modal data,
  • for detection of change, outliers, frauds, or attacks,
  • new interactive learning protocols and application scenarios, e.g., brain-computer interfaces, crowdsourcing, ...
  • in application in data-intensive science,
  • in applications with real-world deployment,
  • Techniques for Combined Interactive Adaptive Learning
  • methods combining adaptive, active, semi-supervised, or transfer learning techniques,
  • cost-aware methods and methods for estimating the impact of employing additional resources, such as data or processing capacities, on the learning progress,
  • methodologies for the evaluation of such techniques, and comparative studies,
  • methods for automating the control of an interactive adaptive learning process.


Important dates

The following timeline shows the most important dates for the workshop.

  • Submission open

    22 April 2022

    You can submit your contributions via EasyChair.

  • Submission deadline EXTENDED

    12 June 2022
    27 June 2022

  • Notification POSTPONED

    11 July 2022
    20 July 2022

  • Camera Ready EXTENDED

    25 July 2022
    3 August 2022

  • Workshop (Half Day)

    23 September 2022

    Co-Located With The The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery (ECML PKDD 2022).

Submit your contribution

You can submit your contribution via EasyChair. Please use the link below.

Submission is now closed.

Full Paper Track

The full paper track covers new innovative contributions in the area of interactive adaptive learning. If you have a new method already evaluated briefly, a new tool to simplify interaction or some new insights the community might benefit from, please submit a regular paper. The page limit is 8-16 pages (excluding references).

Submission Deadline: 27 June 2022

Extended Abstract Track

The extended abstract track is ideal to discuss new ideas in the area of interactive adaptive learning. We encourage you to submit open challenges in research or industrial applications to initiate a discussion and find colleagues to collaborate with. The page limit is 2-4 pages (excluding references).

Submission Deadline: 27 June 2022

Indexed Publishing

All accepted papers will be published at ceur-ws.org (indexed by e.g. google scholar) or within Springer LNCS proceedings depending on the number of submissions. Reviews are single-blind.

LNCS Style

The paper must be be written in English and contain author names, affiliations, and email addresses. The paper must be in PDF using the LNCS format. See instructions here.

Presentation

All accepted papers are presented in spotlight talks and/or poster sessions. At least one author of each accepted paper must be registered to the workshop.

Invited Talks

Isabelle Guyon (Prof. U. Paris-Saclay, USA Researcher INRIA, President ChaLearn)      
Title: Active meta-learning
While Deep Learning keeps obtaining big successes in AI application, improving performance merely by increasing dataset size or computational resources is not going to be sustainable. Transfer learning, and its generalization to multiple data sources and target domains, called meta-learning, is offering a path towards more efficient use of data and resources, leveraging experience gained from task to task by learning systems capable of "learning to learn". The next step to make progress is to incorporate an active selection of tasks and/or models to accelerate meta-learning, i.e. to perform "active meta-learning". This can be performed not only by using heuristic search or Bayesian optimization, but also by involving reinforcement learning. Indeed, active meta-learning can be cast as a Reveal game, a Markov decision process of difficulty intermediary between multi-armed bandits and POMDP. We will illustrate how active meta-learning problems have been solved with various techniques on several benchmarks and challenges, including the recent IJCNN/AutoML-conf 2022 "Meta-learning from learning curves" challenges, in which RL techniques such as DDQN fare well. The work presented was done in collaboration with Lisheng Sun, Zhengying Liu, Nathan Grinsztajn, and Manh Hung Nguyen

Isabelle Guyon is passionate about promoting artificial intelligence and machine learning methods to a wide audience. While she was working at Clopinet, she founded ChaLearn - a non-profit organisation which organises machine learning challenges, which she chairs. Today, ChaLearn is still setting up challenges in partnership with local authorities such as the Île-de-France region, or with major companies such as Dassault or RTE. [Text by universite-paris-saclay.fr]

Program

The full proceedings of the workshop are available here: Full proceedings

Time Program Presenter/Author
14:30 - 16:30 Session 1:
5m Introduction
60m Invited Talk: Title: Active meta-learning Isabelle Guyon
15m A Concept for Automated Polarized Web Content Annotation based on Multimodal Active Learning    M. Herde, D. Huseljic, J. Mitrović, M. Granitzer, B. Sick
20m BioSegment: Active Learning segmentation for 3D imaging    B. Rombaut, J. Roels, Y. Saeys
20m Enhancing Active Learning with Weak Supervision and Transfer Learning by Leveraging Information and Knowledge Sources    L. Rauch, D. Huseljic, B. Sick
Break
17:00 - 18:05 Session 2:
15m Accelerating Diversity Sampling for Deep Active Learning By Low-Dimensional Representations    S. Gilhuber, M. Berrendorf, Y. Ma, T. Seidl
20m A Practical Evaluation of Active Learning Approaches for Object Detection    J. Schneegans, M. Bieshaar, B. Sick
20m Certifiable Active Class Selection in Multi-Class Classification    M. Senz, M. Bunse, K. Morik
10m Closing and information about scikit-activeml D. Kottke

Committee

Organizing Committee:
ial2022 (at) easychair.org

Daniel Kottke

daniel.kottke (at) uni-kassel.de
University of Kassel, Germany

Georg Krempl

g.m.krempl (at) uu.nl
Utrecht University, Netherlands

Barbara Hammer

bhammer (at) techfak.uni-bielefeld.de
University of Bielefeld, Germany

Andreas Holzinger

a.holzinger (at) hci-kdd.org
University of Natural Resources and Life Sciences Vienna, Austria

Steering Committee:

Vincent Lemaire

vincent.lemaire (at) orange.com
Orange Labs, France

Robi Polikar

polikar (at) rowan.edu
Rowan University, USA

Bernhard Sick

bsick (at) uni-kassel.de
University of Kassel, Germany

Adrian Calma

adrian.calma (at) uni-kassel.de
University of Kassel, Germany

Program Committee:

Mirko Bunse (Dortmund University)
Marek Herde (University of Kassel)
Martin Holena (Institute of Computer Science)
Denis Huseljic (University of Kassel)
Dino Ienco (INRAE Montpellier)
Jörg Schlötterer (University of Duisburg-Essen)
Christin Seifert (University of Duisburg-Essen)
Vinicius Souza (Pontifícia Universidade Católica do Paraná)
Myra Spiliopoulou (University of Magdeburg)